Check for missing values

Univariate Analysis for the continuous variables

Univariate Analysis of the descrete variables

Checking dependent variable

Comparison charts using different variables by depandent variable

Comparing Categorical data by Personal Loan

Bivariate Analysis

Model Building - Approach

  1. Data preparation
  2. Partition the data into train and test set.
  3. Built a CART model on the train data.
  4. Tune the model and prune the tree, if required.
  5. Test the data on test set.

Logistic Regression

Insights:

Build Decision Tree Model

We have 90.99% of positive.

Visualizing the Decision Tree

Reducing over fitting

Recall has improved for both train and test set after hyperparameter tuning and we have a generalized model.

Visualizing the Decision Tree

Cost Complexity Pruning

For the remainder, we remove the last element in clfs and ccp_alphas

Visualizing the Decision Tree

Visualizing the Decision Tree

Comparing all the decision tree models

Decision tree model with hyperparameter tuning has given the best recall score on data.

Conclusion and Recommendations